Bruno Didier Olivier Capron

Prof. Dr. Bruno Didier Olivier Capron

Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 November 2022 in Processes
Verified
Journal Article
Open access
PDF file
Ruan de Rezende FariaRuan de Rezende Faria
Ruan de Rezende Faria
BCBruno Didier Olivier Capron
Bruno Didier Olivier Capron
Argimiro Resende SecchiArgimiro Resende Secchi
Argimiro Resende Secchi
Mauricio Bezerra de Souza JúniorMauricio Bezerra de Souza Júnior
Mauricio Bezerra de Souza Júnior
This paper presents a literature review of reinforcement learning (RL) and its applications to process control and optimization. These applications were evaluated from a new perspective on simulation-based offline training and process demonstrations, policy deployment with transfer learning (TL) and the challenges of integrating it by proposing a feasible approach to online process control. The study elucidates how learning from demonstrations can be accomplished through imitation learning (IL) and reinforcement learning, and presents a hyperparameter-optimization framework to obtain a feasible algorithm and deep neural network (DNN). The study details a batch process control experiment using the deep-deterministic-policy-gradient (DDPG) algorithm modified with adversarial imitation learning.

1 January 2023 in Processes
Verified
Journal Article
Open access
PDF file
Ruan de Rezende FariaRuan de Rezende Faria
Ruan de Rezende Faria
BCBruno Didier Olivier Capron
Bruno Didier Olivier Capron
Mauricio Bezerra de Souza JúniorMauricio Bezerra de Souza Júnior
Mauricio Bezerra de Souza Júnior
Argimiro Resende SecchiArgimiro Resende Secchi
Argimiro Resende Secchi
This paper reviews real-time optimization from a reinforcement learning point of view. The typical control and optimization system hierarchy depend on the layers of real-time optimization, supervisory control, and regulatory control. The literature about each mentioned layer is reviewed, supporting the proposal of a benchmark study of reinforcement learning using a one-layer approach. The multi-agent deep deterministic policy gradient algorithm was applied for economic optimization and control of the isothermal Van de Vusse reactor. The cooperative control agents allowed obtaining sufficiently robust control policies for the case study against the hybrid real-time optimization approach.

1 August 2021 in Journal of Petroleum Science and Engineering
Verified
Journal Article
Closed access
SGSergio Andres Castaño Giraldo
Sergio Andres Castaño Giraldo
RSR.C. Supelano
R.C. Supelano
TDT.C. D’aVila
T.C. D’aVila
BCBruno Didier Olivier Capron
Bruno Didier Olivier Capron
LRL.D. Ribeiro
L.D. Ribeiro
Argimiro Resende SecchiArgimiro Resende Secchi
Argimiro Resende Secchi

6 April 2025 in Computers & Chemical Engineering
Verified
Journal Article
Closed access
JTJosé Rodrigues Torraca
José Rodrigues Torraca
BCBruno Didier Olivier Capron
Bruno Didier Olivier Capron
Argimiro Resende SecchiArgimiro Resende Secchi
Argimiro Resende Secchi

1 May 2025 in Chemical Engineering Research and Design
Verified
Journal Article
Closed access
Ruan de Rezende FariaRuan de Rezende Faria
Ruan de Rezende Faria
BCBruno Didier Olivier Capron
Bruno Didier Olivier Capron
Argimiro Resende SecchiArgimiro Resende Secchi
Argimiro Resende Secchi
Mauricio Bezerra de Souza JúniorMauricio Bezerra de Souza Júnior
Mauricio Bezerra de Souza Júnior

19 June 2026
Verified
Conference Paper
Closed access
JNJosé R. Torraca Neto
José R. Torraca Neto
SGSergio Andres Castaño Giraldo
Sergio Andres Castaño Giraldo
MCMario C. M. M. Campos
Mario C. M. M. Campos
GCGustavo Luís Rodrigues Caldas
Gustavo Luís Rodrigues Caldas
BCBruno Didier Olivier Capron
Bruno Didier Olivier Capron
Argimiro Resende SecchiArgimiro Resende Secchi
Argimiro Resende Secchi
Offshore natural gas compression systems are characterized by strong hydraulic coupling, nonlinear behaviour, and strict safety constraints, particularly in high-CO2 production environments. Conventional decentralized PID control with anti-surge protection ensures reliable local regulation but often leads to poor plant-wide coordination and persistent offsets when multiple compression trains, recycle loops, and separation units interact dynamically. Although multivariable control strategies such as model predictive control can address these issues, their industrial application remains limited by modeling effort, computational demand, and robustness concerns. This work presents a hybrid supervisory control framework in which reinforcement learning (RL) augments an existing PI-based architecture for an offshore gas compression system with membrane-based CO2 separation. A Proximal Policy Optimization (PPO) agent is trained on a dynamic digital-twin model of export, CO2, injection, and bypass compression trains with shared headers, recycle flows, and thermal constraints. The RL agent acts exclusively at the supervisory level, providing bounded incremental adjustments to pressure and bypass setpoints, while all regulatory PI loops, anti-surge protections, and safety logic remain unchanged. Closed-loop simulations under representative disturbance scenarios show that the RL-supervised architecture significantly improves plant-wide coordination. Compared to fixed-setpoint PI operation, total tracking error (IAE) and time-weighted error (ITAE) are reduced by approximately 54% and 56%, respectively, using smooth, low-magnitude supervisory actions. In addition, RL achieves performance close to that of a nonlinear MPC benchmark based on a random-shooting, MPPI (Model-Predictive Path Integral) formulation, while requiring substantially lower online computational effort. The results demonstrate that RL can be effectively integrated as a supervisory layer in offshore gas compression systems without replacing established industrial control infrastructure, although additional safety mechanisms are still required to ensure stricter constraint satisfaction.